Papers › Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension
Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension
Yi Tay, Anh Tuan Luu, Siu Cheung Hui
Sequence encoders are crucial components in many neural architectures for learning to read and comprehend. This paper presents a new compositional encoder for reading comprehension (RC). Our proposed encoder is not only aimed at being fast but also expressive. Specifically, the key novelty behind our encoder is that it explicitly models across multiple granularities using a new dilated composition mechanism. In our approach, gating functions are learned by modeling relationships and reasoning over multi-granular sequence information, enabling compositional learning that is aware of both long and short term information. We conduct experiments on three RC datasets, showing that our proposed encoder demonstrates very promising results both as a standalone encoder as well as a complementary building block. Empirical results show that simple Bi-Attentive architectures augmented with our proposed encoder not only achieves state-of-the-art / highly competitive results but is also considerably faster than other published works.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Open-Domain Question Answering | SearchQA | Bi-Attention + DCU-LSTM | EM | - | #10 of 14 | Archive leaderboard | report |
| Open-Domain Question Answering | SearchQA | Bi-Attention + DCU-LSTM | F1 | - | #10 of 14 | Archive leaderboard | report |
| Open-Domain Question Answering | SearchQA | Bi-Attention + DCU-LSTM | N-gram F1 | 59.5 | #10 of 14 | Archive leaderboard | report |
| Open-Domain Question Answering | SearchQA | Bi-Attention + DCU-LSTM | Unigram Acc | 49.4 | #10 of 14 | Archive leaderboard | report |
| Question Answering | NarrativeQA | BiAttention + DCU-LSTM | BLEU-1 | 36.55 | #7 of 10 | Archive leaderboard | report |
| Question Answering | NarrativeQA | BiAttention + DCU-LSTM | BLEU-4 | 19.79 | #7 of 10 | Archive leaderboard | report |
| Question Answering | NarrativeQA | BiAttention + DCU-LSTM | METEOR | 17.87 | #7 of 10 | Archive leaderboard | report |
| Question Answering | NarrativeQA | BiAttention + DCU-LSTM | Rouge-L | 41.44 | #7 of 10 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections